Persona vectors form within the first 0.22% of LLM pretraining and remain effective for steering post-trained models, with continued refinement and transfer to other models.
Persona: Dynamic and compositional inference-time personality control via activation vector algebra.ArXiv, abs/2602.15669
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.
citing papers explorer
-
Tracing Persona Vectors Through LLM Pretraining
Persona vectors form within the first 0.22% of LLM pretraining and remain effective for steering post-trained models, with continued refinement and transfer to other models.
-
The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
LLMs organize prompted social roles along a dominant, stable, and causally steerable granularity axis in representation space that runs from micro to macro levels.